{
 "id": "Helsinki-NLP/multiun",
 "owner": "Helsinki-NLP",
 "name": "multiun",
 "downloads": 8623,
 "likes": 14,
 "last_modified": "2024-02-27T16:59:52.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{eisele-chen-2010-multiun,\n    title = \"{M}ulti{UN}: A Multilingual Corpus from United Nation Documents\",\n    author = \"Eisele, Andreas  and\n      Chen, Yu\",\n    booktitle = \"Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)\",\n    month = may,\n    year = \"2010\",\n    address = \"Valletta, Malta\",\n    publisher = \"European Language Resources Association (ELRA)\",\n    url = \"http://www.lrec-conf.org/proceedings/lrec2010/pdf/686_Paper.pdf\",\n    abstract = \"This paper describes the acquisition, preparation and properties of a corpus extracted from the official documents of the United Nations (UN). This corpus is available in all 6 official languages of the UN, consisting of around 300 million words per language. We describe the methods we used for crawling, document formatting, and sentence alignment. This corpus also includes a common test set for machine translation. We present the results of a French-Chinese machine translation experiment performed on this corpus.\",\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}